© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193353
    Prev
    Next
    INDEX
    Explanations

    casual sexual encounters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icycle
    0.41
     Da
    0.41
    襦
    0.40
    Da
    0.37
     ハート
    0.37
     யூ
    0.37
     Cor
    0.37
    Wax
    0.37
     🥰
    0.37
    马拉
    0.37
    POSITIVE LOGITS
     casual
    0.91
     hook
    0.84
     Casual
    0.82
    Casual
    0.79
     promiscu
    0.76
    casual
    0.71
     Hook
    0.70
     casually
    0.70
     hooking
    0.69
    hook
    0.67
    Activations Density 0.054%

    No Known Activations